projects / platform / upstream / dldt.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ed444bf) | patch
Fix preserving names of output layers after TopK NGraph transformation (#843)
authorRoman Kazantsev <roman.kazantsev@intel.com>
Mon, 15 Jun 2020 07:29:02 +0000 (12:29 +0500)
committerGitHub <noreply@github.com>
Mon, 15 Jun 2020 07:29:02 +0000 (10:29 +0300)
commit683c93e011a9c5cb3b309e0ba870a590a5b95eb1
treef83bf0932b1224db0a95c14f02e736b82d359885tree | snapshot
parented444bf9f4dda442bd2da51140f45631163e0e55commit | diff
Fix preserving names of output layers after TopK NGraph transformation (#843)

* Fix preserving names of output layers after TopK NGraph transformation

It helps to infer semantic-segmentation-adas-0001 model. See CVS-31977.

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix a test for TopK

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix TopK NGraph transformation and its test

Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
inference-engine/src/transformations/src/transformations/convert_opset1_to_legacy/convert_topk_to_topk_ie.cpp diff | blob | history
inference-engine/src/transformations/src/transformations/convert_opset3_to_opset2/convert_topk3.cpp diff | blob | history
inference-engine/tests/functional/inference_engine/transformations/convert_topk3_test.cpp diff | blob | history
Domain: Machine Learning / ML Framework;